Climate variables used as response: - sfcWind,
tas, pr: original scale daily,
reduced scale: hourly - clt, rsds:
original scale monthly, reduced scale: daily
Training: All models are trained using ERA5 in reduced scale as observations. Training data perdiod: 1980 - 2015.
Validation Period: 2015-01-02 00:00:00 to 2023-12-30 23:00:00
Response variable to predict: upscaled ERA5 (daily or monthly)
Predictors variables: daily scale the variables
sfcWind, tas, pr,
tasmax, tasmin and psl and in a
monthly scale clt, rsdt,rsds ,
the month , hour, sun’s elevation & azimuth and the daily daylight
amount in seconds.
| Metric | xgboost | cnn | naive | lstm |
|---|---|---|---|---|
| mae | 0.64 | 0.82 | 0.83 | 0.71 |
| cor | 0.99 | 0.99 | 0.98 | 0.99 |
| ratio_of_sd | 0.99 | 1.01 | 0.98 | 0.98 |
| KGE | 0.98 | 0.98 | 0.98 | 0.98 |
| amplitude_mae | 1.03 | 1.09 | 1.95 | 1.07 |
| maximum_difference | 1.49 | 1.43 | 1.44 | 1.38 |
| sign_correlation | 0.89 | 0.79 | 0.91 | 0.87 |
| extreme_correlation | 0.81 | 0.76 | 0.71 | 0.84 |
| qqplot_mae | 0.06 | 0.35 | 0.09 | 0.38 |
| acf_mae | 0.02 | 0.04 | 0.03 | 0.01 |
| extremogram_mae | 0.02 | 0.02 | 0.01 | 0.01 |
Observations: cumulative distribution (Detrended QQ), dependency structure (ACF), and extremes (Extremogram, using 0.97 cut off).
Daily/Monthly gruped: Maximum hour histogram (only in daily variables), Amplitude distribution.
Hourly/Daily grouped: Mean profile per hour within days (or weeks witihin season)
In all plots, grey color represent the true ERA5 signal.